Triple
T16473451
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Invermark |
E400125
|
entity |
| Predicate | hasNearbyWaterBody |
P1489
|
FINISHED |
| Object | Water of Lee |
E97463
|
NE FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Water of Lee | Statement: [Invermark, hasNearbyWaterBody, Water of Lee]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Water of Lee Context triple: [Invermark, hasNearbyWaterBody, Water of Lee]
-
A.
Water of Lee
chosen
Water of Lee is a tributary stream of the North Esk River in Scotland, known for flowing through rural landscapes before joining the main river.
-
B.
Fairlop Waters
Fairlop Waters is a large country park and leisure facility in northeast London known for its lake, golf course, and outdoor recreation activities.
-
C.
Luggie Water
Luggie Water is a small river in central Scotland that flows through North Lanarkshire, including the town of Coatbridge, before joining the River Kelvin.
-
D.
The Long Water
The Long Water is a picturesque ornamental lake in London's Kensington Gardens, forming the western half of the Serpentine.
-
E.
Sheerwater
Sheerwater is a residential suburb of Woking in Surrey, England, known for its mid-20th-century housing estates and proximity to local industrial and commercial areas.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69d87f2dac988190b74d6e185fa88ba4 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e32dd266c48190991a1484eb2f7bcc |
completed | April 18, 2026, 7:08 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a004f5d16008190bd874080e86b8a2f |
completed | May 10, 2026, 9:26 a.m. |
Created at: April 10, 2026, 5:11 a.m.